quickdraw-MobileVITV2-1.0-Pretrained
This model is a fine-tuned version of shehan97/mobilevitv2-2.0-imagenet1k-256 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.9671
- eval_accuracy: 0.7622
- eval_runtime: 16.2585
- eval_samples_per_second: 15376.569
- eval_steps_per_second: 30.077
- epoch: 6.2626
- step: 55048
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0008
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 21